文档介绍：: .
系统仿真学报 种基于关键点精确配对的点云曲面匹配方法。通过采用基于曲率信息的改进 3D-SIFT 算法，提取点
云数据的关键点；将关键点处的 FPFH 特征描述以及模型中心点到关键点的向量与模型主趋势的夹
角作为约束条件获取精确的关键点匹配点对集合；在此基础上求解刚体变换参数实现模型曲面的初
始匹配；进而使用 ICP 算法进行二次优化，实现模型曲面的精确匹配。实验表明，此方法既能解决
关键点匹配精度问题，又能很好地解决匹配效率的问题。与其它匹配算法相比，此方法的匹配精度
明显优于对比算法。
关键词：尺度不变特征变换；快速点特征直方图；主趋势；刚体变换参数；迭代最近点
中图分类号：TP391 文献标志码：A
DOI: .-0146
Point Cloud Surface Matching Method Based on Precise Matching of Critical Point
NING Xiaojuan1,2, LI Chunxu1, WANG Jiahao1, TANG Jing1,WANG Yinghui3，JIN Haiyan1,2
( of Computer Science and Engineering, Xi’an University of Technology, Xi’an 710048, China; Provincial Key Laboratory of Network
Computing and Security Technology, Xi'an 710048, China; of Artificial Intelligence and Computer, Jiangnan University, Wuxi, Jiangsu 214122)
Abstract: To solve the low matching efficiency and insufficient accuracy of the feature-based point cloud
surface matching method during critical point matching, a point cloud surface matching method based on t
he pairing exaction of critical points is proposed. An improved 3D-SIFT algorithm based on curvature inf
ormation is presented to extract the critical points. Take FPFH feature, the angle between the vector from t
he center to critical points and the principal direction of the model as constraints to obtain exact critical po
int matching point pair set. On this basis, two progressive steps are proposed, which contain initial matchi
ng and accurate matching. The initial matching of the model surface is implemented by the rigid body tran